API Lists

This section mainly describes secure, easy-to-use graph construction APIs for app users or high-level frameworks to build models and set model graphs, operators in the graphs, and the inputs, outputs, and other operator attributes.

aclgrph APIs

API	Function	Header File/Library File
aclgrphParseCaffe	Parses a Caffe model into a graph.	Header files #include <parser/tensorflow_parser.h> #include <parser/caffe_parser.h> Library file: libfmk_parser.so Header file: #include <parser/onnx_parser.h> Library file: libfmk_onnx_parser.so The Atlas A2 training products / Atlas A2 inference products does not support the Caffe framework. The Atlas A3 training products / Atlas A3 inference products does not support the Caffe framework.
aclgrphParseONNX	Parses an ONNX model into a graph.
aclgrphParseONNXFromMem	Parses an ONNX model loaded to the memory into a graph.
aclgrphParseTensorFlow	Parses a TensorFlow model into a graph.
aclgrphBuildInitialize	Initializes model build, for allocating resources.	Header file: #include <ge/ge_ir_build.h> Library file: libge_compiler.so
aclgrphBuildFinalize	Destroys allocations after model building.
aclgrphBuildModel	Builds an input graph into an offline model adapted to the Ascend AI Processor and saves it to the memory buffer.
aclgrphBundleBuildModel	The difference between this API and aclgrphBuildModel is that this API applies to the weight update scenario. After the offline model cache is generated using the aclgrphBundleBuildModel API, aclgrphBundleSaveModel needs to be called to flush the cache to disks.
aclgrphBundleSaveModel	Serializes an offline model to a file.
aclgrphConvertToWeightRefreshableGraphs	Converts the original graph into a group of graphs whose weights can be updated by passing the const node name array.
aclgrphDumpGraph	Dumps the input graph to a text file.
aclgrphGetIRVersion	Obtains the version number of the API related to model build.
aclgrphGenerateForOp	Builds a graph based on the single-operator information or JSON file of a single-operator.
aclgrphSaveModel	Serializes an offline model to a file.
aclgrphSetOpAttr	Sets node attributes to modify a graph.
aclgrphCalibration	Quantizes a graph. For details about the application scenarios, see Quantization.	Header file: #include <amct/acl_graph_calibration.h> Library file: libamctacl.so
aclgrphProfCreateConfig	Creates a Profiling configuration.	Header file: #include <ge/ge_prof.h> Library file: libmsprofiler.so The Atlas 200I/500 A2 inference products does not support the Caffe framework.
aclgrphProfDestroyConfig	Destroys the Profiling configuration.
aclgrphProfFinalize	Finalizes Profiling.
aclgrphProfInit	Initializes Profiling and sets Profiling parameters. (Currently, you can specify the path for saving profile data files.)
aclgrphProfStart	Starts profile data collection.
aclgrphProfStop	Stops profile data collection.

Session APIs

Category	API	Function	Header File/Library File
Session	Session Constructor and Destructor	Constructs or destroys an object of class Session.	Header file: #include <ge/ge_api.h> Library file: libge_runner.so This feature is not supported by the Atlas 200I/500 A2 inference products .
	AddGraph	Adds a graph to a Session, in which a unique graph ID is generated.
	AddGraphWithCopy	Adds a graph to a Session, in which a unique graph ID is generated.
	BuildGraph	Builds the graph of a specified ID to generate an executable model. This API is synchronous.
	CompileGraph	Synchronously compiles the graph corresponding to the specified ID. Compared with BuildGraph, this API provides only the graph compilation function and does not generate executable models. BuildGraph contains the graph build process, initializes the memory resources required by the model after the process, and generates an executable model.
	ExecuteGraphWithStreamAsync	Runs the graph of a specified ID and returns the execution result. This API is asynchronous.
	GEInitialize	Initializes GE.
	GetCompiledGraphSummary	Queries the summary information about the graph compilation result. The summary information includes the feature memory size, const memory size, number of streams and events, and whether the memory can be updated.
	GEFinalize	Finalizes GE and destroys associated allocations.
	GEGetErrorMsg	Obtains and clears the error message returned by other API call failure in the calling process or thread.
	GEGetErrorMsgV2	Obtains and clears the error message returned by other API call failure in the process or thread.
	GEGetWarningMsg	Obtains and clears the warning message returned by other API call failure in the process or thread.
	GEGetWarningMsgV2	Obtains and clears the warning message returned by other API call failure in the calling process or thread.
	GetSessionId	Obtains the session ID.
	GetVariables	Queries variables and obtains Tensor information of all variable operators or of a specified variable operator within a Session.
	IsGraphNeedRebuild	Determines whether a graph needs to be recompiled.
	LoadGraph	Binds a graph with a specified ID to a stream in asynchronous graph execution scenarios.
	PaRemapped	Determines whether the memory can be quickly recovered when an uncorrectable error (UCE) occurs in the memory.
	RegisterCallBackFunc	Registers a callback function.
	RegisterExternalAllocator	Registers an external allocator to the GE. This applies to the scenario where the user's memory pool is used.
	RemoveGraph	Removes a graph specified by graphId from a Session.
	RunGraph	Runs the graph of a specified ID and returns the execution result. This API is synchronous.
	RunGraphAsync	Runs the graph of a specified ID and returns the running result. This API is asynchronous.
	RunGraphDistribute	Runs the graph corresponding to a specified ID synchronously after the input refdata node is partitioned, and outputs the running result.
	RunGraphWithStreamAsync	Runs the graph of a specified ID and returns the running result. This API is asynchronous. This API is used to build, load, and run graphs.
	SaveGraphsToPb	This API is deprecated. Avoid using it. Saves graphs in a session as a .pb file. Weight sharing in a session is supported. That is, if two graphs in a session have the same weight, only one weight is saved.
	SetGraphConstMemoryBase	Sets the const memory base address of a graph.
	SetGraphFixedFeatureMemoryBase	Sets the memory base address of the fixed feature of a graph.
	SetGraphFixedFeatureMemoryBaseWithType	Sets the base address of the fixed feature memory of different memory types in a graph.
	ShardGraphs	This API is deprecated. Avoid using it. This API shards graphs in a session based on the AddGraph sequence. Sharded graphs are saved in the memory.
	ShardGraphsToFile	This API is deprecated. Avoid using it. Shard a graph in a session based on the AddGraph sequence. Sharded graphs are saved as .pb files.
	UpdateGraphFeatureMemoryBase	Updates the feature memory base address of a graph.
	UpdateGraphRefreshableFeatureMemoryBase	Updates the base address of the feature memory that can be updated except fixed memory.
	UnregisterExternalAllocator	Destroys the allocator registered by the user based on the stream. This applies to the scenario where the user's memory pool is used.
GESession	GeSession Constructor and Destructor	Constructs and destructs an object of class GeSession.	Header file: #include <ge/ge_api_v2.h> Library file: libge_runner_v2.so This feature is not supported by the Atlas 200I/500 A2 inference products .
	AddGraph	Adds a graph to a GeSession, in which a unique graph ID is generated.
	AddGraphClone	Adds a graph to a GeSession, in which a unique graph ID is generated.
	CompileGraph	Synchronously compiles the graph corresponding to the specified ID.
	GEFinalizeV2	Finalizes the GE and releases GE resources.
	GEGetErrorMsgV3	Obtains and clears the error messages returned by other failed API calls in the same process or thread.
	GEGetWarningMsgV3	Obtains and clears the warning information returned by other failed API calls in the same process or thread.
	GEInitializeV2	Initializes GE for running.
	GetCompiledGraphSummary	Queries the summary information about the graph compilation result. The summary information includes the feature memory size, const memory size, numbers of streams and events, and whether the memory can be updated.
	GetCompiledModel	Obtains the serialized model after graph compilation.
	GetSessionId	Obtains the ID of a session.
	IsGraphNeedRebuild	Determines whether a graph needs to be rebuilt.
	LoadGraph	Loads a graph and prepares for its execution, including allocating and managing resources such as memory and computational streams required for graph execution.
	RegisterCallBackFunc	Registers a callback function.
	RegisterExternalAllocator	Registers a user's Allocator to the GE. This applies to the scenario where the user's memory pool is used.
	RemoveGraph	Removes a graph with a specified ID from the current GeSession.
	RunGraph	Runs the graph of a specified ID and returns the execution result. This API is synchronous.
	RunGraphAsync	Runs the graph of a specified ID and returns the running result. This API is asynchronous.
	RunGraphWithStreamAsync	Runs the graph of a specified ID and returns the execution result. This API is asynchronous.
	SetGraphConstMemoryBase	Sets the const memory base address of a graph.
	SetGraphFixedFeatureMemoryBaseWithType	Sets the base address of the fixed feature memory of different memory types in a graph.
	UpdateGraphFeatureMemoryBase	Updates the feature memory base address of a graph.
	UpdateGraphRefreshableFeatureMemoryBase	Updates the base address of the feature memory that can be updated except fixed memory.
	UnregisterExternalAllocator	Destroys the allocator registered by the user based on the stream. This applies to the scenario where the user's memory pool is used.

ES APIs

Category	API	Function	Header File/Library File
Class and structure	CompliantNodeBuilder	Node builder class. This class is used to build graph nodes that comply with the IR specifications. This class provides chain APIs to define the IR input, output, and attributes of a node, ensuring that the generated node complies with the IR specifications. This class is called internally by ES generated APIs. If you directly build a graph by calling an ES generated API, you do not need to be aware of this class. To customize ES APIs, use the capabilities provided by this class to build nodes.	#include "compliant_node_builder.h"
	EsCGraphBuilder	C-style graph builder structure, which is an internal implementation class of C and C++. C users call esb_funcs.h to build graphs, and C++ users call external APIs of the EsGraphBuilder class.	#include <es_c_graph_builder.h>
	EsCTensorHolder	C-style output type of the ES API. C users call esb_funcs.h to build graphs, and C++ users call external APIs of the EsTensorHolder class.	#include <es_c_tensor_holder.h>
	EsGraphBuilder	Graph builder class. This class is used by C++ users to build computational graphs. This class provides methods for creating graph elements such as inputs, setting private attributes, building final graphs, and calling the conversion logic of the ES generated API of C by the inline function of the ES generated API of C++.	#include "es_graph_builder.h"
	EsTensorHolder	Node output expression class. This class is used for C++ graph building. This class provides the tensor operation APIs of C and provides various operations on node outputs, including setting the data type, format, and shape, setting private attributes, and performing arithmetic operations.	#include "es_tensor_holder.h"
	EsTensorLike	Generic EsTensorHolder class. This class is used to convert scalar and vector values into EsTensorHolder objects so that the C++ graph building APIs can directly transfer values for graph building.	#include <es_tensor_like.h>
Function	EsCreateGraphBuilder	Creates a graph builder instance.	#include <ge/es_funcs.h>
	EsDestroyGraphBuilder	Releases graph builder resources.
	EsCreateGraphInputWithDetails	Creates an input on a graph.
	EsCreateGraphInput	Creates a data input on a graph.
	EsSetDataType	Sets the data type of a tensor. If no data type is specified, the default value float is used.
	EsSetFormat	Sets the memory format of a tensor. If no format is set, the default value ND is used.
	EsSetShape	Sets the shape of a tensor. If no shape is set, the default value [] is used, that is, a scalar.
	EsSetOriginSymbolShape	Sets the symbolic expression of the tensor shape. If it is not set, there is no symbolic information by default.
	EsCreateConstInt64	Creates a Const node of the int64 type.
	EsCreateConstInt32	Creates a Const node of the int32 type.
	EsCreateConstUInt64	Creates a Const node of the uint64 type.
	EsCreateConstUInt32	Creates a Const node of the uint32 type.
	EsCreateConstFloat	Creates a Const node of the float type.
	EsCreateVectorInt64	Creates a vector constant of the int64 type.
	EsCreateVectorInt32	Creates a vector constant of the int32 type.
	EsCreateVectorUInt64	Creates a vector constant of the uint64 type.
	EsCreateVectorUInt32	Creates a vector constant of the uint32 type.
	EsCreateVectorFloat	Creates a vector constant of the float type.
	EsCreateScalarInt64	Creates a scalar constant of the int64 type.
	EsCreateScalarInt32	Creates a scalar constant of the int32 type.
	EsCreateScalarUInt64	Creates a scalar constant of the uint64 type.
	EsCreateScalarUInt32	Creates a scalar constant of the uint32 type.
	EsCreateScalarFloat	Creates a scalar constant of the float type.
	EsCreateVariable	Creates a variable node.
	EsSetGraphOutput	Sets the output of a graph.
	EsBuildGraphAndReset	Returns the pointer to the ge::Graph instance. The ownership is transferred to the caller.
	EsGetOwnerBuilder	Returns the snapshot of the EsCGraphBuilder instance. The ownership is not transferred.
	EsGetProducer	Returns the snapshot of the ge::GNode instance.
	EsAddControlEdge	Connects control edges.
	EsCreateEsCTensor	Creates an EsCTensor by a C user.
	EsCreateEsCTensorFromFile	Creates an EsCTensor by a C user using a binary file.
	EsSetInt64AttrForGraph	Sets the int64 attribute of a graph.
	EsSetStringAttrForGraph	Sets the string attribute of a graph.
	EsSetBoolAttrForGraph	Sets the Boolean attribute of a graph.
	EsSetInt64AttrForTensor	Sets the int64 attribute of a tensor.
	EsSetStringAttrForTensor	Sets the string attribute of a tensor.
	EsSetBoolAttrForTensor	Sets the Boolean attribute of a tensor.
	EsSetInt64AttrForNode	Sets the int64 attribute of a node.
	EsSetStringAttrForNode	Sets the string attribute of a node.
	EsSetBoolAttrForNode	Sets the Boolean attribute of a node.

Data Structures and APIs

Category	Data Structure/API	Function	Header File/Library File
Class and structure	Allocator	Supports the external allocator registered by users.	Header file: #include <ge/ge_allocator.h>
	ArgDescInfo	ArgDescInfo class. This class describes the address information specified by Args, a kernel input parameter. It semantically expresses Args-specified addresses and specifies the usage and related information about each address.	Header file: #include <graph/arg_desc_info.h>
	ArgsFormatSerializer	ArgsFormat serialization information.	Header file: #include <graph/arg_desc_info.h>
	AttrValue	Stores attribute values.	Header file: #include <graph/attr_value.h> Library file: libgraph_base.so
	CompiledGraphSummary	Provides brief information about the graph build result.	Header file: #include <ge/ge_graph_compile_summary.h> Library file: libge_compiler.so
	CtInferShapeContext	Inherited from InferShapeContext, CtInferShapeContext is used for shape inference during compilation and provides APIs for compilation.	Header file: #include <ct_infer_shape_context.h>
	CtInferShapeRangeContext	Inherited from InferShapeRangeContext, CtInferShapeRangeContext is used for ShapeRange inference during compilation and provides APIs for compilation.	Header file: #include <ct_infer_shape_range_context.h>
	CustomPassContext	Obtains the custom pass context object.	Header file: #include <register/register_custom_pass.h> Library file: libregister.so
	DecomposePass	Decomposes the pass class.	Header file: #include <ge/fusion/pass/decompose_pass.h>
	ExternalWeightDesc	Details the external weights to be persisted into a disk.	Header file: #include <ge/ge_graph_compile_summary.h> Library file: libge_compiler.so
	FeatureMemory	Stores feature memory information.	Header file: #include <ge/ge_feature_memory.h> Library file: libge_compiler.so
	FusionBasePass	Fusion pass.	Header file: #include <ge/fusion/pass/fusion_base_pass.h>
	FusionPassRegistrationData	Fusion pass registration class.	Header file: #include <ge/fusion/pass/fusion_pass_reg.h>
	GeUtils	Provides utilities for GE graph modification, such as shape inference, node support verification, and graph optimization.	Header file: #include <ge/ge_utils.h> Library file: libge_compiler.so
	GNode	Constructs node data of a graph.	Header file: #include <graph/gnode.h> Library file: libgraph.so
	Graph	Constructs graph-related classes.	Header file: #include <graph/graph.h> Library file: libgraph.so
	GraphBuffer	Stores the cached data of graphs.	Header file: #include <graph/graph_buffer.h> Library file: libgraph_base.so
	InferenceContext	Obtains the inference context object and sets the shape and data type of the object for resource operators.	Header file: #include <graph/inference_context.h>
	InferFormatFuncRegister	Registers the operator InferFormat function. This API is referenced by other header files and is not directly called by operator developers.	Header file: #include <graph/operator_factory.h>
	InferShapeFuncRegister	Registers the operator infershape function. This API is referenced by other header files and is not directly called by operator developers.	Header file: #include <graph/operator_factory.h>
	InferValueRangeFuncRegister	Registers the operator InferValueRangeFuncRegister function. This API is referenced by other header files and is not directly called by operator developers.	Header file: #include <graph/operator_factory.h>
	InputTensorInfo	Input tensor information.	Header file: #include <ge/ge_api_types.h>
	KernelLaunchInfo	Provides APIs for creating and managing tasks delivered to devices. The APIs allow developers to set or obtain the launch information about the tasks to be delivered to devices.	Header file: #include <graph/kernel_launch_info.h>
	LogicalStreamAllocationInfo	Allocates information to logical streams.	Header file: #include <ge/ge_graph_compile_summary.h> Library file: libge_compiler.so
	MatchResult	A matching result on the graph by means of PatternMatcher. The result contains the matching node.	Header file: #include <ge/fusion/match_result.h> Library file: libge_compiler.so
	ModelBufferData	Serialized model data in the memory buffer.	Header file: #include <ge/ge_ir_build.h> Library file: libge_compiler.so
	Operator	Operator class.	Header file: #include <graph/operator.h> Library file: libgraph.so
	OperatorCreatorRegister	Registers an operator prototype. This API is referenced by other header files. Therefore, it is not directly called by operator developers.	Header file: #include <graph/operator_factory.h>
	OperatorFactory	An internal associated API, which is referenced by other header files and is not directly called by operator developers.	Header file: #include <graph/operator_factory.h>
	OpLibRegister	The APIs provided by the OpLibRegister class are internal associated APIs. Currently, the class provides the registration function for the custom operator dynamic library so that the custom operator project framework can register specified initialization functions. You do not need to pay attention to these APIs.	Header file: #include <register/op_lib_register.h>
	OutputTensorInfo	Output tensor information.	Header file: #include <ge/ge_api_types.h>
	PassRegistrar	Receives fusion pass registration information and registers it with the global singleton.	Header file: #include <ge/fusion/pass/fusion_pass_reg.h>
	Pattern	Defines a template for graph structure matching. It receives a graph and uses it to describe the graph structure to be matched.	Header file: #include <ge/fusion/pattern.h> Library file: libge_compiler.so
	PatternFusionPass	Pattern fusion class.	Header file: #include <ge/fusion/pass/pattern_fusion_pass.h>
	PatternMatcher	Tool class for subgraph matching. It receives pattern definition and a graph to be matched. It uses the pattern to perform graph matching, provides the MatchNext API to return matching results one by one.	Header file: #include <ge/fusion/pattern_matcher.h> Library file: libge_compiler.so
	PatternMatcherConfig	A class used to configure the PatternMatcher behavior.	Header file: #include <ge/fusion/pattern_matcher_config.h> Library file: libge_compiler.so
	PatternMatcherConfigBuilder	An auxiliary class used to construct PatternMatcherConfig.	Header file: #include <ge/fusion/pattern_matcher_config.h> Library file: libge_compiler.so
	ShapeAndType	Sets and obtains the shape and data type of an object.	Header file: #include <graph/inference_context.h>
	StreamAllocationSummary	Stream allocation summary.	Header file: #include <ge/ge_graph_compile_summary.h> Library file: libge_compiler.so
	StreamPassContext	Context object for the logical stream allocation pass.	Header file: #include <register/register_custom_pass.h> Library file: libregister.so
	SubgraphRewriter	A tool class for graph modification. It receives a range on a graph and a replacement graph, and uses the replacement graph to replace the nodes in the given range on the graph.	Header file: #include <ge/fusion/graph_rewriter.h> Library file: libge_compiler.so
	SubgraphInput	Describes an input tensor of a subgraph.	Header file: #include <ge/fusion/subgraph_boundary.h>
	SubgraphOutput	Describes an output tensor of a subgraph.	Header file: #include <ge/fusion/subgraph_boundary.h>
	SubgraphBoundary	Defines a subgraph boundary.	Header file: #include <ge/fusion/subgraph_boundary.h>
	VerifyFuncRegister	Registers the operator verifyFunc function. This API is referenced by other header files and is not directly called by operator developers.	Header file: #include <graph/operator_factory.h>
Function	ConvertToAscendString	A template function. It accepts a template parameter T and converts it to the AscendString type. Converts strings of different types to those of the AscendString type.	Header file: #include <graph/operator_reg.h>
Function	ConvertToListAscendString	Defines a template function ConvertToListAscendString to convert strings of different types to those of the AscendString type.	Header file: #include <graph/operator_reg.h>
Macro	BROADCAST_INFER	Encapsulated macro of common functions, facilitating the development of the InferShape function. This function sets the output shape based on the shapes of two inputs. This macro sets shape only, and does not set dtype.	Header file: #include <graph/operator_reg.h>
	COMMON_INFER_FUNC_REG	Registers the InferShape function of an operator.	Header file: #include <graph/operator_reg.h>
	ELMTWISE_INFER_SHAPEANDTYPE	Encapsulated macro of common functions, facilitating the development of the InferShape function. This API sets the output shape and dtype based on the input shape and dtype.	Header file: #include <graph/operator_reg.h>
	IMPLEMT_COMMON_INFERFUNC	Encapsulates the Common_InferShape function of an operator.	Header file: #include <graph/operator_reg.h>
	IMPLEMT_INFERFORMAT_FUNC	Encapsulates the inferFormat function of an operator.	Header file: #include <graph/operator_reg.h>
	IMPLEMT_INFERFUNC	Encapsulates the InferShape function of an operator.	Header file: #include <graph/operator_reg.h>
	IMPLEMT_VERIFIER	Encapsulates the Verify function of an operator.	Header file: #include <graph/operator_reg.h>
	INFER_FORMAT_FUNC_REG	Registers the InferFormat implementation of an operator.	Header file: #include <graph/operator_reg.h>
	INFER_FUNC_REG	Registers the InferShape function of an operator.	Header file: #include <graph/operator_reg.h>
	REG_FUSION_PASS	Registers the function of a custom fusion pass.	Header file: #include <ge/fusion/pass/pattern_fusion_pass.h> Library file: libge_compiler.so
	REG_DECOMPOSE_PASS	Graph modification function in the 1-to-N scenario.	Header file: #include <ge/fusion/pass/decompose_pass.h> Library file: libge_compiler
	REGISTER_CUSTOM_PASS	Registers the function of a custom pass.	Header file: #include <register/register_custom_pass.h> Library file: libregister.so
	VERIFY_FUNC_REG	Registers the Verify function of an operator.	Header file: #include <graph/operator_reg.h>
	Prototype Definition (REG_OP)	Prototype definition API.	Header file: #include <graph/operator_reg.h>
	Prototype Definition Derivative APIs	Prototype definition derivative APIs.	Header file: #include <graph/operator_reg.h>
Interface C	aclGetCustomOpLibPath	Obtains the path of the custom operator library.	Header file: #include <register/register_base.h>
	GeSessionLoadGraph	Applies only to the scenario where the graph is executed asynchronously. The specified session is used to bind the graph with the specified value of graph ID to the corresponding stream.	Header file: #include <ge/ge_api.h> Library file: libge_runner.so
	GeSessionExecuteGraphWithStreamAsync	Runs the graph of a specified ID using the specified session instance and returns the execution result. This API is asynchronous.
	GEStreamAllocationSummaryGetAllNodes	Obtains all nodes of the root graph and subgraphs.	Header file: #include <ge/ge_graph_compile_summary.h> Library file: libge_compiler.so
	GEStreamAllocationSummaryGetAttachedStreamIds	Obtains the IDs of the auxiliary secondary logical streams of the root graph and subgraphs.
	GEStreamAllocationSummaryGetHcclFollowedStreamNums	Obtains the actual number of physical streams of the communication secondary stream corresponding to the root graph and subgraphs.
	GEStreamAllocationSummaryGetLogicalStreamIds	Obtains the logical stream IDs of the root graph and subgraphs.
	GEStreamAllocationSummaryGetPhysicalStreamNums	Obtains the actual number of physical streams of the root graph and subgraphs.
	GEStreamAllocationSummaryGetStringInfos	Obtains the logical stream information strings of the root graph and subgraphs.
	GEStreamAllocationSummaryGetStreamGraphs	Obtains the stream graphs of the root graph and subgraphs.
	GEStreamAllocationSummaryGetUsrStreamLabels	Obtains the user stream labels of the root graph and subgraphs.
	GEStreamAllocationSummaryIsAssignedByStreamPass	Specifies whether the root graph and subgraphs are allocated by the user-registered stream allocation pass.
	GetRegisteredIrDef	Obtains the prototype definition of a registered IR operator.	Header file: #include <ge/ge_api.h> Library file: libge_runner.so
Enumerations	ArgDescType	Type of an Args address.	Header file: #include <graph/arg_desc_info.h>
	HiddenInputSubType	Hidden input address type of ArgDescInfo.	Header file: #include <graph/arg_desc_info.h>
	DumpFormat	Format of dump files.	Header file: #include <graph/graph.h>
	MemoryType	-	Header file: #include <ge/ge_api_types.h>
	ProfDataTypeConfig	Configuration file of the Profiling data type.	Header file: #include <ge/ge_prof.h> Library file: libmsprofiler.so This feature is not supported by the Atlas 200I/500 A2 inference products .
	ProfilingAicoreMetrics	Profiling AI Core metrics.
Configuration parameters	aclgrphBuildInitialize Configuration Parameters	-	Header file: #include <ge/ge_api_types.h>
	aclgrphBuildModel Configuration Parameters	-	Header file: #include <ge/ge_api_types.h>
	Configuration Parameters of Model Parsing APIs	-	Header file: #include <ge/ge_api_types.h>
	Command-Line Options	-	Header file: #include <ge/ge_api_types.h> This feature is not supported by the Atlas 200I/500 A2 inference products .
	Attribute Name List	Attribute name that can be set for the SetAttr API.	Header file: #include <ge/ge_api_types.h>
Error codes	GE_ERRORNO	GE error codes and macro information.	Header file: #include <ge/ge_api_error_codes.h> Library file: libge_common_base.so